Jedrzej Kosinski
d483297496
Moved Recraft nodes to nodes_recraft.py ( #48 )
2025-05-26 20:53:48 -07:00
Jedrzej Kosinski
e945b1b47e
Moved Luma nodes to nodes_luma.py ( #47 )
2025-05-26 20:53:48 -07:00
Christian Byrne
65eb4104a9
Fix image upload for Luma: only include Content-Type header field if it's set explicitly ( #40 )
2025-05-26 20:53:48 -07:00
Christian Byrne
22c7bacffc
Fix runway image upload and progress polling ( #39 )
2025-05-26 20:53:48 -07:00
Jedrzej Kosinski
0fcf869c9e
Add Realistic Image and Logo Raster styles for Recraft v3 ( #38 )
2025-05-26 20:53:48 -07:00
thot experiment
a0b991c4ba
add better error propagation to veo2 ( #37 )
2025-05-26 20:53:48 -07:00
Christian Byrne
36a201cec7
Set Content-Type header when uploading files ( #36 )
2025-05-26 20:53:48 -07:00
Christian Byrne
a55f29662d
Standard CATEGORY system for api nodes ( #35 )
2025-05-26 20:53:48 -07:00
Christian Byrne
ff5fd5d507
Convert Minimax node to use VIDEO output type ( #34 )
2025-05-26 20:53:48 -07:00
Christian Byrne
992a4b0838
Add Runway nodes ( #17 )
2025-05-26 20:53:48 -07:00
Jedrzej Kosinski
34ec6daeee
Add Camera Concepts (luma_concepts) to Luma Video nodes ( #33 )
...
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
2025-05-26 20:53:48 -07:00
Christian Byrne
f074134afd
Add Kling Nodes ( #12 )
2025-05-26 20:53:48 -07:00
Jedrzej Kosinski
a121b74aa4
Add Recraft nodes ( #29 )
2025-05-26 20:53:48 -07:00
thot experiment
a1822fda3d
add veo2, bump av req ( #32 )
2025-05-26 20:53:48 -07:00
Chenlei Hu
5bb148c8bb
[Bug] Remove duplicated option T2V-01 in MinimaxTextToVideoNode ( #31 )
2025-05-26 20:53:48 -07:00
Jedrzej Kosinski
bed5cfec84
Fix image_luma_ref not working ( #28 )
...
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
2025-05-26 20:53:48 -07:00
Jedrzej Kosinski
239fd5dac0
Add rest of Luma node functionality ( #19 )
...
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
2025-05-26 20:53:48 -07:00
Christian Byrne
740caecda5
Refactor util functions ( #20 )
2025-05-26 20:53:48 -07:00
Jedrzej Kosinski
6ebad2d81b
Add Luma nodes ( #16 )
...
Co-authored-by: Robin Huang <robin.j.huang@gmail.com>
2025-05-26 20:53:48 -07:00
Robin Huang
1218567ece
Add function for uploading files. ( #18 )
2025-05-26 20:53:48 -07:00
Christian Byrne
f29a3194b4
Manually add BFL polling status response schema ( #15 )
2025-05-26 20:53:48 -07:00
Jedrzej Kosinski
c6d9c77e86
Added initial BFL Flux 1.1 [pro] Ultra node ( #11 )
2025-05-26 20:53:48 -07:00
Robin Huang
1d24f0a68f
Added Ideogram and Minimax back in.
2025-05-26 20:53:48 -07:00
Robin Huang
ac559a2b76
Update stubs.
2025-05-26 20:53:48 -07:00
Robin Huang
e2efb9b2c2
Revert "Remove polling operations."
...
This reverts commit 8415404ce8fbc0262b7de54fc700c5c8854a34fc.
2025-05-26 20:53:48 -07:00
Robin Huang
c35e12da77
Remove polling operations.
2025-05-26 20:53:48 -07:00
Robin Huang
320fbbbe44
Remove uv.lock
2025-05-26 20:53:48 -07:00
Christian Byrne
bb07ac87fe
[Minimax] Show video preview and embed workflow in ouput ( #7 )
2025-05-26 20:53:48 -07:00
Robin Huang
e772520dcd
Add Minimax Video Generation + Async Task queue polling example ( #6 )
2025-05-26 20:53:39 -07:00
Robin Huang
e7dad1d7db
Add API_NODE and common error for missing auth token ( #5 )
2025-05-26 20:53:39 -07:00
Robin Huang
7290683905
Add staging api.
2025-05-26 20:53:39 -07:00
Robin Huang
6f5caa0879
Add Ideogram generate node.
2025-05-26 20:53:39 -07:00
comfyanonymous
89a84e32d2
Disable initial GPU load when novram is used. ( #8294 )
2025-05-26 16:39:27 -04:00
comfyanonymous
e5799c4899
Enable pytorch attention by default on AMD gfx1151 ( #8282 )
2025-05-26 04:29:25 -04:00
comfyanonymous
a0651359d7
Return proper error if diffusion model not detected properly. ( #8272 )
2025-05-25 05:28:11 -04:00
comfyanonymous
ad3bd8aa49
ComfyUI version 0.3.36
2025-05-24 17:30:37 -04:00
comfyanonymous
5a87757ef9
Better error if sageattention is installed but a dependency is missing. ( #8264 )
2025-05-24 06:43:12 -04:00
Christian Byrne
464aece92b
update frontend package to v1.20.5 ( #8260 )
2025-05-23 21:53:49 -07:00
comfyanonymous
0b50d4c0db
Add argument to explicitly enable fp8 compute support. ( #8257 )
...
This can be used to test if your current GPU/pytorch version supports fp8 matrix mult in combination with --fast or the fp8_e4m3fn_fast dtype.
2025-05-23 17:43:50 -04:00
drhead
30b2eb8a93
create arange on-device ( #8255 )
2025-05-23 16:15:06 -04:00
comfyanonymous
f85c08df06
Make VACE conditionings stackable. ( #8240 )
2025-05-22 19:22:26 -04:00
comfyanonymous
4202e956a0
Add append feature to conditioning_set_values ( #8239 )
...
Refactor unclipconditioning node.
2025-05-22 08:11:13 -04:00
Terry Jia
b838c36720
remove mtl from 3d model file list ( #8192 )
2025-05-22 08:08:36 -04:00
Chenlei Hu
fc39184ea9
Update frontend to 1.20 ( #8232 )
2025-05-22 02:24:36 -04:00
ComfyUI Wiki
ded60c33a0
Update templates to 0.1.18 ( #8224 )
2025-05-21 11:40:08 -07:00
Michael Abrahams
8bb858e4d3
Improve performance with large number of queued prompts ( #8176 )
...
* get_current_queue_volatile
* restore get_current_queue method
* remove extra import
2025-05-21 05:14:17 -04:00
编程界的小学生
57893c843f
Code Optimization and Issues Fixes in ComfyUI server ( #8196 )
...
* Update server.py
* Update server.py
2025-05-21 04:59:42 -04:00
Jedrzej Kosinski
65da29aaa9
Make torch.compile LoRA/key-compatible ( #8213 )
...
* Make torch compile node use wrapper instead of object_patch for the entire diffusion_models object, allowing key assotiations on diffusion_models to not break (loras, getting attributes, etc.)
* Moved torch compile code into comfy_api so it can be used by custom nodes with a degree of confidence
* Refactor set_torch_compile_wrapper to support a list of keys instead of just diffusion_model, as well as additional torch.compile args
* remove unused import
* Moved torch compile kwargs to be stored in model_options instead of attachments; attachments are more intended for things to be 'persisted', AKA not deepcopied
* Add some comments
* Remove random line of code, not sure how it got there
2025-05-21 04:56:56 -04:00
comfyanonymous
10024a38ea
ComfyUI version v0.3.35
2025-05-21 04:50:37 -04:00
comfyanonymous
87f9130778
Revert "This doesn't seem to be needed on chroma. ( #8209 )" ( #8210 )
...
This reverts commit 7e84bf53737879ace37a68dc93e0df7704a53514.
2025-05-20 05:39:55 -04:00
